INDEX

Explanations

the word "ent"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ansa

-0.16

lette

-0.15

ifo

-0.15

 xáº¿p

-0.14

lesh

-0.14

ATES

-0.14

 giochi

-0.14

OUNDS

-0.14

EATURE

-0.14

eldo

-0.14

POSITIVE LOGITS

0.21

encies

0.15

0.14

 Laden

0.14

ECH

0.14

catid

0.14

 WARRANT

0.14

ãĥ³ãĥĶ

0.14

Activations Density 0.000%

the word "ent"

No Comments

No Known Activations