INDEX

Explanations

terms related to boxing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 goose

-0.15

_EL

-0.15

Č↵

-0.14

 GetLastError

-0.14

ugu

-0.14

anmar

-0.14

á»Ļt

-0.14

 Manning

-0.14

,cv

-0.14

ths

-0.14

POSITIVE LOGITS

peri

0.16

æº

0.15

æĺĩ

0.15

 fairness

0.15

.pa

0.14

 Pare

0.14

ãĥĲãĤ¤

0.14

 fair

0.14

.exc

0.14

ç±į

0.13

Activations Density 0.036%

terms related to boxing

No Comments

No Known Activations