INDEX

Explanations

mentions of job-related content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 rubber

-0.17

 Rubber

-0.16

omal

-0.16

umen

-0.15

.pagination

-0.14

.af

-0.14

 Roses

-0.14

azer

-0.14

Ĺ

-0.14

imest

-0.14

POSITIVE LOGITS

antro

0.16

emode

0.16

krit

0.16

_erase

0.15

 molec

0.15

erm

0.14

HIR

0.14

vik

0.14

 Lawson

0.14

atron

0.14

Activations Density 0.007%

mentions of job-related content

No Comments

No Known Activations