INDEX

Explanations

occurrences of the letter 'd' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

anik

-0.15

çĶ

-0.15

ansa

-0.14

ä¹İ

-0.14

ÙĬØ§Ø±

-0.14

ewn

-0.14

ROTO

-0.14

è§Ī

-0.14

ash

-0.14

ogg

-0.14

POSITIVE LOGITS

alm

0.19

udos

0.17

ilet

0.17

forth

0.17

izen

0.15

urement

0.15

ure

0.15

ivers

0.15

recht

0.14

áº£

0.14

Activations Density 0.015%

occurrences of the letter 'd' in various contexts

No Comments

No Known Activations