INDEX

Explanations

terms related to human rights organizations and activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ckt

-0.15

 inval

-0.15

acro

-0.14

BA

-0.13

apol

-0.13

ÃŃr

-0.13

ewis

-0.13

ektor

-0.13

anus

-0.13

yro

-0.13

POSITIVE LOGITS

oli

0.16

reds

0.16

paque

0.15

czy

0.15

vil

0.14

niej

0.14

abled

0.14

ient

0.14

att

0.14

Activations Density 0.012%

terms related to human rights organizations and activities

No Comments

No Known Activations