INDEX

Explanations

elements related to challenges or obstacles in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

lico

-0.15

ÅĽnie

-0.14

ÙĤÙĬ

-0.14

unya

-0.14

anken

-0.13

Ã¤tz

-0.13

ORIES

-0.13

ATES

-0.13

ennie

-0.13

suma

-0.13

POSITIVE LOGITS

er

1.66

ER

0.82

erin

0.76

ers

0.74

erer

0.73

erse

0.72

eru

0.66

erb

0.65

erli

0.64

erland

0.63

Activations Density 0.132%

elements related to challenges or obstacles in various contexts

No Comments

No Known Activations

elements related to challenges or obstacles in various contexts

No Comments

No Known Activations