INDEX

Explanations

references to specific individuals or groups mentioned within the text

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

oyer

-0.21

udeau

-0.17

ForKey

-0.16

 Libert

-0.15

 Burr

-0.15

oward

-0.15

idlo

-0.14

ieved

-0.14

lesc

-0.14

rong

-0.14

POSITIVE LOGITS

0.14

yles

0.14

áºŃu

0.14

swire

0.14

 munch

0.13

urum

0.13

bsites

0.13

IGH

0.13

VOKE

0.13

Activations Density 0.408%

references to specific individuals or groups mentioned within the text

No Known Activations