INDEX

Explanations

action verbs and terms related to outcomes and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

uhl

-0.16

otic

-0.14

isas

-0.14

stances

-0.14

ega

-0.14

olik

-0.14

ofs

-0.13

led

-0.13

á»įi

-0.13

learning

-0.13

POSITIVE LOGITS

ÙİØ§ÙĨ

0.17

UNUSED

0.15

0.14

ÐµÑĢÐ±

0.14

åĦĢ

0.14

ritten

0.14

yectos

0.14

à¤ķà¤¨

0.14

LocalizedString

0.14

"){

0.14

Activations Density 0.003%

action verbs and terms related to outcomes and evaluations

No Comments

No Known Activations