INDEX

Explanations

references to specific individuals and their placeholder pages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ierge

-0.15

Ø²Ùħ

-0.14

kills

-0.14

dra

-0.14

nie

-0.14

pread

-0.14

ì¸µ

-0.13

ìĽĮíģ¬

-0.13

çĵ¦

-0.13

TickCount

-0.13

POSITIVE LOGITS

cket

0.17

onium

0.17

onom

0.16

Lal

0.15

 sext

0.15

 ante

0.14

 Bast

0.14

ysz

0.14

Activations Density 0.006%

references to specific individuals and their placeholder pages

No Comments

No Known Activations