INDEX

Explanations

mentions of specific individuals

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Ø²Ùħ

-0.17

rompt

-0.16

ogui

-0.15

igo

-0.15

engin

-0.15

untu

-0.15

inho

-0.15

ãĤīãģĽ

-0.15

/REC

-0.14

icom

-0.14

POSITIVE LOGITS

 listed

0.15

 arrest

0.15

_locs

0.15

ugas

0.14

IDA

0.14

 ancestors

0.14

 past

0.14

.helpers

0.13

 Records

0.13

Activations Density 0.006%

mentions of specific individuals

No Known Activations