INDEX

Explanations

words and concepts indicating quality, evaluation, or classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

dra

-0.15

reich

-0.15

-0.14

æĬľ

-0.13

kest

-0.13

feld

-0.13

ermann

-0.13

Ke

-0.13

-pic

-0.13

POSITIVE LOGITS

aldi

0.17

ekk

0.16

isco

0.15

yb

0.15

ardy

0.15

ilde

0.14

\grid

0.14

iaux

0.14

parity

0.14

PÅĻed

0.14

Activations Density 0.065%

words and concepts indicating quality, evaluation, or classification

No Comments

No Known Activations