INDEX

Explanations

the substring "ent" in words

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

eneg

-0.17

 Barrel

-0.16

isia

-0.15

.si

-0.15

á»ģ

-0.15

 barrel

-0.14

ikan

-0.14

endants

-0.14

rol

-0.14

 McCart

-0.14

POSITIVE LOGITS

llen

0.14

tet

0.14

dock

0.14

OfWork

0.14

iten

0.14

 Bers

0.14

pered

0.13

orrow

0.13

.deploy

0.13

rede

0.13

Activations Density 0.000%

the substring "ent" in words

No Comments

No Known Activations