INDEX

Explanations

occurrences of the word "that" 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÑĥÑĢÑĥ

-0.16

eid

-0.14

åĭ¢

-0.14

casts

-0.14

jÃŃt

-0.14

Ø§Ø¡

-0.13

.cljs

-0.13

theid

-0.13

acen

-0.13

quo

-0.13

POSITIVE LOGITS

way

1.24

-way

0.89

Way

0.89

way

0.88

WAY

0.83

Way

0.77

.way

0.77

_way

0.77

WAY

0.71

 ways

0.69

Activations Density 0.071%

occurrences of the word "that" in various contexts

No Comments

No Known Activations