INDEX

Explanations

the repeated phrase "im" indicating locations or contexts within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

xic

-0.18

ctor

-0.17

omy

-0.16

ilet

-0.15

emente

-0.15

illet

-0.15

ICON

-0.14

ffi

-0.14

ners

-0.14

ish

-0.14

POSITIVE LOGITS

ozor

0.16

elu

0.16

artz

0.15

ologne

0.15

psilon

0.15

ornings

0.15

neas

0.15

 tÃ¼k

0.14

radu

0.14

opes

0.14

Activations Density 0.003%

the repeated phrase "im" indicating locations or contexts within a text

No Comments

No Known Activations