INDEX

Explanations

references to a specific location or entity that is significant in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

sch

-0.17

esc

-0.17

eval

-0.16

ene

-0.15

iers

-0.15

ential

-0.15

ermen

-0.15

HB

-0.15

embr

-0.15

POSITIVE LOGITS

ly

0.17

nt

0.16

thur

0.15

shr

0.15

otty

0.14

vard

0.14

bitrary

0.14

antz

0.14

land

0.14

ced

0.13

Activations Density 0.027%

references to a specific location or entity that is significant in context

No Comments

No Known Activations

references to a specific location or entity that is significant in context

No Comments

No Known Activations