INDEX

Explanations

references to specific locations and events in a historical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ãģĭãģ®

-0.14

ierarchy

-0.14

nable

-0.14

ÙģØ³

-0.13

inode

-0.13

/tty

-0.13

ãĤĬãģ¨

-0.13

ERRU

-0.13

SError

-0.13

iddi

-0.13

POSITIVE LOGITS

ley

0.18

/OR

0.16

acre

0.16

 latter

0.15

oller

0.15

itarian

0.15

land

0.14

Ð°Ð»Ð¾Ð²

0.14

AccessException

0.14

orious

0.14

Activations Density 0.321%

references to specific locations and events in a historical context

No Comments

No Known Activations