INDEX

Explanations

the word "all" and its variations in different contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eta

-0.15

ÃĹ↵↵

-0.14

ette

-0.14

zia

-0.14

ï»¿#

-0.14

etto

-0.14

oce

-0.14

åģ¥

-0.14

gz

-0.14

_EXTERN

-0.14

POSITIVE LOGITS

/sources

0.22

 sources

0.21

 source

0.21

/source

0.20

 SOUR

0.20

sources

0.19

 Sources

0.19

ourced

0.18

.sources

0.18

Sources

0.18

Activations Density 0.007%

the word "all" and its variations in different contexts

No Comments

No Known Activations