INDEX

Explanations

the presence of specific temporal or location phrases within 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 @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

kah

-0.17

oretical

-0.17

gether

-0.16

orem

-0.16

allee

-0.15

oret

-0.15

venge

-0.15

aring

-0.15

withstanding

-0.14

è²´

-0.14

POSITIVE LOGITS

shore

0.17

obot

0.16

quis

0.15

sha

0.15

 order

0.15

ÙĦØª

0.15

unc

0.14

col

0.14

 Batt

0.14

iqu

0.14

Activations Density 1.363%

the presence of specific temporal or location phrases within the text

No Comments

No Known Activations