INDEX

Explanations

the occurrence of the word "become" in various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

arna

-0.17

.TestTools

-0.16

ouro

-0.16

usal

-0.16

 ActionTypes

-0.15

.scalablytyped

-0.14

 Harm

-0.14

ural

-0.14

ë²

-0.14

Ð°Ð¼Ð¸

-0.14

POSITIVE LOGITS

orage

0.16

Ã©gor

0.16

ildo

0.16

eh

0.16

imin

0.14

.criteria

0.14

etus

0.14

ATIVE

0.14

nech

0.14

lest

0.14

Activations Density 0.043%

the occurrence of the word "become" in various forms

No Comments

No Known Activations