INDEX

Explanations

various types of cuisines and food-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

akin

-0.16

iro

-0.15

ould

-0.15

odor

-0.14

inou

-0.14

enda

-0.14

ptions

-0.14

cases

-0.14

oupon

-0.14

olini

-0.14

POSITIVE LOGITS

 style

0.40

-style

0.39

style

0.37

 Style

0.33

_style

0.31

-inspired

0.30

 styled

0.28

 STYLE

0.28

Style

0.28

(style

0.26

Activations Density 0.100%

various types of cuisines and food-related terms

No Comments

No Known Activations