INDEX

Explanations

references to specific years, particularly those significant in historical contexts, along with notable personalities associated with those years

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

opleft

-0.17

gx

-0.15

adera

-0.15

apesh

-0.15

ellite

-0.15

 immense

-0.15

lain

-0.15

ced

-0.15

ois

-0.14

pole

-0.14

POSITIVE LOGITS

ervation

0.17

legg

0.16

/w

0.15

-disable

0.15

aydÄ±

0.15

ERTICAL

0.14

enh

0.14

 behalf

0.14

iode

0.14

vert

0.13

Activations Density 0.066%

references to specific years, particularly those significant in historical contexts, along with notable personalities associated with those years

No Comments

No Known Activations