INDEX

Explanations

instances of directional or positional indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

nech

-0.15

native

-0.15

 native

-0.15

(strtolower

-0.15

orque

-0.14

andon

-0.14

illard

-0.14

ibern

-0.14

 Cata

-0.14

acom

-0.14

POSITIVE LOGITS

ektÃ¶r

0.15

lej

0.15

arius

0.15

ÑĤÐ¸Ð½

0.15

vej

0.14

 ìĺĨ

0.14

Î³Î¿Î½

0.14

snap

0.14

æºĢ

0.14

Ðĩ

0.14

Activations Density 0.000%

instances of directional or positional indicators

No Comments

No Known Activations