INDEX

Explanations

references to measures of time, place, or identifiers related to events and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

zier

-0.19

zell

-0.16

 miÃªu

-0.16

lington

-0.15

à¥ĭà¤ķà¤°

-0.15

decess

-0.15

okable

-0.15

vice

-0.15

AMED

-0.14

elmet

-0.14

POSITIVE LOGITS

ort

0.17

erman

0.16

er

0.15

UZ

0.15

Âł

0.15

TT

0.15

 Sorting

0.14

dt

0.14

å£

0.14

uz

0.14

Activations Density 0.027%

references to measures of time, place, or identifiers related to events and actions

No Comments

No Known Activations