INDEX

Explanations

phrases that discuss potential and capabilities related to a subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

its

-0.15

yw

-0.14

ossa

-0.14

weit

-0.14

adt

-0.14

ashi

-0.14

 Attribution

-0.13

 laut

-0.13

.easy

-0.13

.dw

-0.13

POSITIVE LOGITS

 entirety

0.19

ascar

0.18

 nature

0.17

 confines

0.16

 essence

0.16

 extent

0.15

ackbar

0.15

Î³Î¿Î½

0.15

ehr

0.14

 spirit

0.14

Activations Density 0.164%

phrases that discuss potential and capabilities related to a subject

No Comments

No Known Activations