INDEX

Explanations

specific syntax or formatting elements in code, particularly related to data structures and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ubb

-0.15

ADOS

-0.14

elage

-0.14

ervas

-0.14

eva

-0.14

ubs

-0.13

 Peters

-0.13

uggle

-0.13

ltre

-0.13

istas

-0.13

POSITIVE LOGITS

LOB

0.15

thern

0.15

.sheet

0.15

-gnu

0.14

IENT

0.14

ÐĽÐ¬

0.14

0.13

venir

0.13

Activations Density 0.120%

specific syntax or formatting elements in code, particularly related to data structures and functions

No Comments

No Known Activations