INDEX

Explanations

instances of events or performances showcasing unique features or artistic presentations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ipt

-0.16

tha

-0.15

ns

-0.14

Lug

-0.14

emes

-0.14

osit

-0.14

apsed

-0.14

abyrin

-0.14

ycop

-0.14

ni

-0.13

POSITIVE LOGITS

 prominently

0.16

ŀæĢ§

0.15

lix

0.14

lif

0.14

lap

0.14

.Addr

0.14

GROUND

0.14

tte

0.14

://%

0.14

åĿĤ

0.13

Activations Density 0.026%

instances of events or performances showcasing unique features or artistic presentations

No Comments

No Known Activations