INDEX

Explanations

references to geographic areas or regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

geh

-0.15

Ã¶st

-0.15

acic

-0.14

_FILENO

-0.14

_REGISTRY

-0.13

aravel

-0.13

/stdc

-0.13

utow

-0.13

hit

-0.13

POSITIVE LOGITS

quina

0.19

stvo

0.16

most

0.15

egg

0.15

 Tomorrow

0.15

azu

0.14

stva

0.14

ductor

0.14

ment

0.14

RetVal

0.14

Activations Density 0.037%

references to geographic areas or regions

No Comments

No Known Activations