INDEX

Explanations

references to significant political figures and organizations

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

olis

-0.15

Hao

-0.15

iset

-0.15

Ì£

-0.14

inst

-0.14

 Injectable

-0.14

Éµ

-0.14

-mf

-0.14

stein

-0.13

ivation

-0.13

POSITIVE LOGITS

/utility

0.16

unsch

0.14

wt

0.14

ombine

0.14

 corpor

0.14

ycz

0.14

ritel

0.14

InView

0.14

rollo

0.14

Î¯Îº

0.13

Activations Density 0.085%

references to significant political figures and organizations

No Comments

No Known Activations