INDEX

Explanations

terms related to journalism and journalists

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

querque

-0.16

weis

-0.15

yster

-0.15

itzer

-0.15

loh

-0.15

WEEN

-0.14

eyer

-0.14

 gross

-0.14

_mgr

-0.14

SOR

-0.13

POSITIVE LOGITS

ecs

0.15

rys

0.15

/media

0.14

@update

0.14

.nextDouble

0.14

ebra

0.14

ystack

0.14

nika

0.14

isÃŃ

0.13

ÏĦÏĥ

0.13

Activations Density 0.012%

terms related to journalism and journalists

No Comments

No Known Activations