INDEX

Explanations

verbs related to change or transformation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ifu

-0.16

uci

-0.16

Ð»Ð¾Ð¹

-0.14

uilder

-0.14

 fullest

-0.14

inki

-0.13

vÄĽd

-0.13

 olsun

-0.13

ivil

-0.13

keley

-0.13

POSITIVE LOGITS

 into

0.94

into

0.80

 Into

0.79

Into

0.70

_into

0.67

 INTO

0.66

.into

0.53

 vÃło

0.40

 menjadi

0.34

nto

0.34

Activations Density 0.142%

verbs related to change or transformation

No Comments

No Known Activations