INDEX

Explanations

code structures indicating class and method definitions

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

ighth

-0.15

zar

-0.15

åĬª

-0.14

emax

-0.14

oppable

-0.14

Ec

-0.14

-toggler

-0.14

ambi

-0.14

inus

-0.13

onium

-0.13

POSITIVE LOGITS

wicklung

0.17

 entr

0.15

EDIA

0.15

gnore

0.15

XD

0.14

braco

0.14

mdl

0.14

.TabStop

0.14

lage

0.14

ÑĤÐ°Ð»

0.14

Activations Density 0.037%

code structures indicating class and method definitions

No Comments

No Known Activations