INDEX

Explanations

instances of structured text markers such as titles or sections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

LinkId

-0.16

hea

-0.15

Ø³ÙĨÚ¯

-0.15

BaseContext

-0.15

èĳĹ

-0.14

fal

-0.14

isme

-0.14

HELL

-0.14

.band

-0.14

HandlerContext

-0.13

POSITIVE LOGITS

edn

0.16

-controls

0.15

 Hari

0.14

afone

0.14

orney

0.14

Who

0.14

 eyes

0.14

who

0.14

’

0.13

elib

0.13

Activations Density 0.099%

instances of structured text markers such as titles or sections

No Comments

No Known Activations