INDEX

Explanations

references to dates, particularly years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

å¸°

-0.16

erno

-0.15

 Phen

-0.15

iges

-0.15

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

-0.15

ean

-0.14

cate

-0.14

AppComponent

-0.14

lector

-0.14

POSITIVE LOGITS

ãĥ³ãĤ°ãĥ«

0.15

hed

0.15

lord

0.15

ourt

0.15

__;↵

0.15

 Hedge

0.15

reich

0.14

bed

0.14

Î´Î·

0.14

ths

0.14

Activations Density 0.048%

references to dates, particularly years

No Comments

No Known Activations