INDEX

Explanations

occurrences of programming functions and their parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

_REUSE

-0.18

ãģ¹

-0.14

äºĭ

-0.14

ariate

-0.13

ategory

-0.13

iktig

-0.13

Ã¸r

-0.13

alc

-0.13

nyder

-0.13

åĽ

-0.13

POSITIVE LOGITS

rets

0.18

Ð¾Ð±Ð°

0.17

reno

0.15

imoto

0.15

oppel

0.15

ammers

0.15

Falsy

0.14

sett

0.14

urai

0.14

MBER

0.14

Activations Density 0.035%

occurrences of programming functions and their parameters

No Comments

No Known Activations