INDEX

Explanations

instances of strong subjective judgments or evaluations

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

wert

-0.17

 BuzzFeed

-0.15

anela

-0.15

itize

-0.15

usercontent

-0.14

 Ð£ÐºÑĢÐ°ÑĹÐ½Ð°

-0.14

OffsetTable

-0.14

ittings

-0.14

alat

-0.14

rick

-0.14

POSITIVE LOGITS

æ³ī

0.17

 general

0.15

 material

0.15

via

0.15

ropa

0.15

iae

0.14

 pieces

0.14

udio

0.14

ãĥ¼ãĥģ

0.14

pl

0.14

Activations Density 0.000%

instances of strong subjective judgments or evaluations

No Comments

No Known Activations