INDEX

Explanations

references to "that" or "this" as a demonstrative pronoun indicating particular items or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

BuilderFactory

-0.18

rud

-0.17

rpc

-0.16

 navr

-0.16

 Means

-0.15

pery

-0.15

theid

-0.15

ãĤ¤ãĥ¤

-0.15

zyst

-0.15

POSITIVE LOGITS

way

0.56

-way

0.36

Way

0.35

way

0.33

_way

0.31

.way

0.30

WAY

0.30

Way

0.28

 direction

0.26

 ways

0.25

Activations Density 0.021%

references to "that" or "this" as a demonstrative pronoun indicating particular items or concepts

No Comments

No Known Activations