INDEX

Explanations

keywords related to locations or organizations

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

iej

-0.15

\grid

-0.15

tingham

-0.14

plication

-0.14

uesday

-0.14

yper

-0.14

adesh

-0.14

tub

-0.13

iences

-0.13

icrous

-0.13

POSITIVE LOGITS

 Fool

0.15

 fool

0.15

 GLint

0.15

ungs

0.15

jac

0.14

ATEG

0.14

vej

0.14

eyer

0.14

otine

0.14

_DIRS

0.14

Activations Density 0.044%

keywords related to locations or organizations

No Comments

No Known Activations