INDEX

Explanations

references to judgment and the act of judging

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

kes

-0.16

fe

-0.15

idel

-0.15

kke

-0.15

ca

-0.15

ereg

-0.15

 Attribution

-0.15

adem

-0.15

rong

-0.14

apo

-0.14

POSITIVE LOGITS

ãģ¨ãģĵãĤį

0.16

bras

0.16

è·Ŀ

0.15

multipart

0.15

Poz

0.15

anka

0.14

 favor

0.14

nable

0.14

Jud

0.14

rf

0.14

Activations Density 0.027%

references to judgment and the act of judging

No Comments

No Known Activations