INDEX

Explanations

expressions of personal feelings and identities

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

inson

-0.17

umbing

-0.16

utt

-0.15

Å

-0.15

usters

-0.14

 prÅ¯bÄĽhu

-0.14

aternity

-0.13

ysis

-0.13

utor

-0.13

 Trevor

-0.13

POSITIVE LOGITS

OffsetTable

0.16

Ø§Ùĩ

0.15

 similarly

0.15

ÏģÎ¹Î¬

0.15

teg

0.15

dice

0.14

isko

0.14

robat

0.14

dex

0.14

 similar

0.14

Activations Density 0.106%

expressions of personal feelings and identities

No Comments

No Known Activations