INDEX

Explanations

references to specific events, actions, or conditions related to notable mistakes or failures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ibir

-0.15

vra

-0.15

Ð»Ð°Ð·

-0.14

.throw

-0.14

auer

-0.14

Î¼Î²

-0.14

ibri

-0.13

ÑĩÐ½Ð°

-0.13

.python

-0.13

rana

-0.13

POSITIVE LOGITS

.cent

0.15

intage

0.15

utures

0.14

etro

0.13

avic

0.13

eper

0.13

etto

0.13

 perg

0.13

ering

0.13

Fut

0.13

Activations Density 0.108%

references to specific events, actions, or conditions related to notable mistakes or failures

No Comments

No Known Activations