INDEX

Explanations

the word "prior" and its variations, indicating a focus on previous experience or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

chin

-0.15

empo

-0.15

avn

-0.15

oton

-0.14

cheon

-0.14

elah

-0.14

leme

-0.14

packing

-0.14

POSITIVE LOGITS

/current

0.22

itize

0.16

imes

0.15

itized

0.15

itar

0.15

ileges

0.14

à¹īà¸ĩ

0.14

umat

0.14

Argb

0.14

Ŀ

0.14

Activations Density 0.010%

the word "prior" and its variations, indicating a focus on previous experience or events

No Comments

No Known Activations