INDEX

Explanations

words related to entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

orer

-0.16

dehy

-0.15

áº¿t

-0.15

wy

-0.15

olley

-0.15

íĤ¨

-0.14

å¡Ķ

-0.14

íĩ´

-0.14

Ð¾Ð´Ð°

-0.14

 Ð½ÐµÐ³

-0.14

POSITIVE LOGITS

unsch

0.15

 support

0.14

 Carm

0.14

åĩ¡

0.14

rounded

0.14

aru

0.14

isko

0.13

stp

0.13

helm

0.13

 Ã¡n

0.13

Activations Density 0.000%

words related to entertainment

No Comments

No Known Activations