INDEX

Explanations

logical conditions and return statements in code

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

inx

-0.14

PARSE

-0.14

 Orth

-0.14

Ã©o

-0.14

ucha

-0.14

 Rect

-0.14

inki

-0.13

mani

-0.13

ÄĻki

-0.13

(strtolower

-0.13

POSITIVE LOGITS

laus

0.16

acles

0.16

yes

0.16

ó

0.15

aines

0.14

YES

0.14

acle

0.14

ego

0.14

IFS

0.14

Activations Density 0.055%

logical conditions and return statements in code

No Comments

No Known Activations