INDEX

Explanations

programming-related terms and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

deaux

-0.17

raq

-0.16

ippo

-0.15

Å¡tÃŃ

-0.15

igua

-0.14

uild

-0.14

 ÙĦØº

-0.14

isans

-0.14

RuleContext

-0.14

utas

-0.14

POSITIVE LOGITS

yne

0.17

oph

0.15

agger

0.15

PTR

0.14

 anim

0.14

inis

0.14

Fal

0.13

 McInt

0.13

anim

0.13

animated

0.13

Activations Density 0.002%

programming-related terms and structures

No Comments

No Known Activations