INDEX

Explanations

occurrences of method calls related to string manipulation

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

WR

-0.16

 Twins

-0.15

reen

-0.15

ours

-0.15

perPage

-0.15

 sÄ±ras

-0.15

ç®±

-0.14

arto

-0.14

ibri

-0.14

ibraltar

-0.14

POSITIVE LOGITS

á»ĳi

0.15

Ģìŀ¥

0.14

CharArray

0.14

DTD

0.14

Rah

0.14

IMD

0.14

Col

0.13

 Deutsch

0.13

olini

0.13

Activations Density 0.046%

occurrences of method calls related to string manipulation

No Comments

No Known Activations