INDEX

Explanations

definite articles and the presence of specific nouns in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

yme

-0.15

çį

-0.15

 tilt

-0.14

èĿ

-0.14

_GAP

-0.14

LETE

-0.14

åĨ

-0.14

eme

-0.14

elli

-0.13

imas

-0.13

POSITIVE LOGITS

oÄŁ

0.17

kich

0.16

ISIBLE

0.14

vais

0.14

onium

0.14

apg

0.14

cstdint

0.14

ryo

0.14

gst

0.14

Ã©nom

0.14

Activations Density 0.075%

definite articles and the presence of specific nouns in the text

No Comments

No Known Activations