INDEX

Explanations

contexts related to food and cooking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

bs

-0.15

spor

-0.15

liers

-0.15

arts

-0.15

 whiskey

-0.14

zan

-0.14

ys

-0.14

_LSB

-0.14

rier

-0.14

POSITIVE LOGITS

alink

0.16

stra

0.15

 Austr

0.14

=findViewById

0.14

Trace

0.14

æ¾

0.14

oser

0.13

 nÃ©t

0.13

seealso

0.13

inch

0.13

Activations Density 0.126%

contexts related to food and cooking

No Comments

No Known Activations