INDEX

Explanations

phrases that indicate actions or conditions related to application processes and decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

orch

-0.15

sson

-0.14

otte

-0.14

ÑĩÑĥÐº

-0.14

ÙħÙĪØ¯

-0.13

è¨¼

-0.13

opsis

-0.13

aid

-0.13

urm

-0.13

Ã³d

-0.13

POSITIVE LOGITS

ammer

0.16

ooter

0.15

IPH

0.15

_defaults

0.15

azon

0.15

atÃ¼rk

0.15

 nale

0.15

/Dk

0.15

GDK

0.15

umb

0.14

Activations Density 0.073%

phrases that indicate actions or conditions related to application processes and decisions

No Comments

No Known Activations