INDEX

Explanations

occurrences of strings and encodings related to database interactions in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

bject

-0.17

Formats

-0.15

udder

-0.14

ively

-0.14

enido

-0.13

gre

-0.13

ucid

-0.13

LocalizedString

-0.13

av

-0.13

POSITIVE LOGITS

echa

0.15

raphics

0.15

ihan

0.15

ilia

0.14

hangi

0.14

opsis

0.14

_NC

0.14

ancel

0.14

ogne

0.14

arrass

0.13

Activations Density 0.010%

occurrences of strings and encodings related to database interactions in programming contexts

No Comments

No Known Activations