INDEX

Explanations

expressions of evaluation and comparison

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ullo

-0.16

hopefully

-0.15

èĢĮ

-0.15

 mÃł

-0.14

opo

-0.14

ince

-0.14

_almost

-0.13

åİŁæĿ¥

-0.13

 èĢĮ

-0.12

DisplayName

-0.12

POSITIVE LOGITS

 however

1.05

 though

0.97

however

0.73

though

0.72

 Though

0.71

Though

0.68

 jedoch

0.65

 However

0.65

 HOWEVER

0.64

 allerdings

0.58

Activations Density 1.288%

expressions of evaluation and comparison

No Comments

No Known Activations