INDEX

Explanations

terms related to health, safety, and social science research

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

inf

-0.16

affen

-0.16

INF

-0.15

conc

-0.15

wares

-0.15

oj

-0.15

usp

-0.15

asse

-0.14

Ð°Ð¶

-0.14

seg

-0.14

POSITIVE LOGITS

.yy

0.20

ç°

0.17

dorf

0.16

/documentation

0.16

 æĴ

0.15

Î´ÎµÎ¹

0.15

 Screw

0.15

.PerformLayout

0.14

nip

0.14

umbing

0.14

Activations Density 0.148%

terms related to health, safety, and social science research

No Comments

No Known Activations

terms related to health, safety, and social science research

No Comments

No Known Activations