INDEX

Explanations

the word "which" 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 @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

alin

-0.15

anchor

-0.15

Ø®Ø§ÙĨÙĩ

-0.15

ians

-0.15

aul

-0.14

ì§Ħ

-0.14

ocs

-0.13

ë²

-0.13

Ø¬Ø§

-0.13

 cuales

-0.13

POSITIVE LOGITS

soever

0.18

phere

0.16

wald

0.16

ÑģÑĮ

0.15

vido

0.14

yal

0.14

sphere

0.14

Sphere

0.14

ptal

0.14

phans

0.13

Activations Density 0.057%

the word "which" in various contexts

No Comments

No Known Activations