INDEX

Explanations

descriptors indicating loudness or intensity 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 @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

alue

-0.17

bare

-0.16

IBE

-0.15

itone

-0.15

imum

-0.14

asal

-0.14

reinterpret

-0.14

 Sink

-0.14

andal

-0.13

ä»ĺãģį

-0.13

POSITIVE LOGITS

ness

0.35

NESS

0.24

 enough

0.17

nes

0.17

halt

0.15

enes

0.15

ening

0.15

0.14

uden

0.14

Trad

0.14

Activations Density 0.038%

descriptors indicating loudness or intensity in various contexts

No Comments

No Known Activations