INDEX

Explanations

references to celebrity-related news and events

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

ICODE

-0.20

AndView

-0.16

rips

-0.15

 Grave

-0.15

][_

-0.14

 Ricardo

-0.14

æ´ª

-0.14

ï¼©

-0.14

.espresso

-0.14

ibr

-0.14

POSITIVE LOGITS

Alv

0.17

ÙĦØ§ÙĨ

0.14

Ø§Ø±Ø³

0.14

anders

0.14

.logic

0.14

,readonly

0.13

oming

0.13

 unspecified

0.13

'S

0.13

Activations Density 0.014%

references to celebrity-related news and events

No Comments

No Known Activations