INDEX

Explanations

indications of coding comments or documentation syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

PCODE

-0.16

lice

-0.16

jspx

-0.15

Ð°ÑĢÑĮ

-0.15

ARRANT

-0.15

STALL

-0.15

 Balt

-0.15

aisal

-0.14

lexport

-0.14

outil

-0.14

POSITIVE LOGITS

tains

0.15

{-

0.15

ode

0.15

ul

0.15

Ð¾Ð³ÐµÐ½

0.15

0.14

idia

0.14

Activations Density 0.035%

indications of coding comments or documentation syntax

No Comments

No Known Activations