INDEX

Explanations

references to entertainment and its related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

pt

-0.16

enny

-0.16

 trÆ°á»Łng

-0.16

ocal

-0.16

aret

-0.15

ps

-0.15

Ã¨ge

-0.15

mist

-0.15

ogl

-0.14

eyer

-0.14

POSITIVE LOGITS

tainment

0.20

EDIUM

0.17

argo

0.15

 entertainment

0.15

apia

0.15

 crude

0.14

 entertain

0.14

angler

0.14

è´¹

0.14

agma

0.14

Activations Density 0.029%

references to entertainment and its related concepts

No Comments

No Known Activations