INDEX

Explanations

references to allegations and accusations in various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

upt

-0.18

ehler

-0.17

lle

-0.15

ality

-0.15

alle

-0.14

angler

-0.14

roe

-0.14

icens

-0.14

 Conv

-0.14

ksi

-0.14

POSITIVE LOGITS

antium

0.15

#echo

0.15

airs

0.15

/request

0.14

Erf

0.14

 Moon

0.14

/assert

0.14

Ã³c

0.14

/problem

0.14

kara

0.14

Activations Density 0.035%

references to allegations and accusations in various contexts

No Known Activations