INDEX

Explanations

sentences that feature questions or impactful statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

elik

-0.16

 ÙħØ«

-0.15

aiser

-0.15

à¸²à¸¢

-0.15

andr

-0.14

erset

-0.14

æ¬

-0.14

essed

-0.14

 disp

-0.14

olan

-0.14

POSITIVE LOGITS

isman

0.15

upon

0.15

 reply

0.14

 then

0.14

 Wein

0.14

RET

0.14

rof

0.14

ating

0.14

å¯¹æĸ¹

0.14

 replied

0.14

Activations Density 0.203%

sentences that feature questions or impactful statements

No Comments

No Known Activations