INDEX

Explanations

references to user interaction or engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

anja

-0.17

estate

-0.16

YY

-0.16

ÑĢÐ¾ÑģÑĤÐ¾

-0.15

 estate

-0.15

retty

-0.15

ãģªãĤĭ

-0.14

setattr

-0.14

ÑĢÐµÑħ

-0.14

_signature

-0.14

POSITIVE LOGITS

HN

0.18

ekler

0.15

ÑĮÐºÐ¾

0.15

CTS

0.15

hod

0.14

col

0.14

 quat

0.14

 amount

0.14

uds

0.13

isman

0.13

Activations Density 0.006%

references to user interaction or engagement

No Comments

No Known Activations