INDEX

Explanations

occurrences of the word "the" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

urgeon

-0.15

ZZ

-0.15

visor

-0.14

á»±

-0.14

anders

-0.14

ÎķÎļ

-0.14

 still

-0.13

 diagnostics

-0.13

Î»Î¬

-0.13

tras

-0.13

POSITIVE LOGITS

ifix

0.16

eneg

0.15

inja

0.15

agu

0.14

agenta

0.14

 kraje

0.14

baru

0.14

YRO

0.13

 ÄĮer

0.13

imuth

0.13

Activations Density 0.135%

occurrences of the word "the" in various contexts

No Comments

No Known Activations