INDEX

Explanations

predominant phrases indicating purpose or key actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

eor

-0.17

enge

-0.16

rire

-0.15

laÄį

-0.15

leftright

-0.15

ornings

-0.14

alth

-0.14

QUIRE

-0.14

tah

-0.14

oad

-0.14

POSITIVE LOGITS

 ÑģÐ¾Ñģ

0.16

0.15

anken

0.15

ÑģÑĤÐ°Ð²

0.15

avigation

0.15

ckt

0.15

assel

0.14

 Nack

0.14

achten

0.14

asis

0.14

Activations Density 0.013%

predominant phrases indicating purpose or key actions

No Comments

No Known Activations