INDEX

Explanations

details about personal information and relationships

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

ency

-0.17

pling

-0.15

ibase

-0.15

ipsis

-0.15

å§Ķ

-0.14

.synthetic

-0.14

 McCabe

-0.14

 Robinson

-0.14

.opendaylight

-0.14

ino

-0.14

POSITIVE LOGITS

etc

0.16

[of

0.14

/or

0.14

ãĥĥãĥĹ

0.14

Decl

0.14

wner

0.13

 Benedict

0.13

appen

0.13

 irrational

0.13

Activations Density 0.007%

details about personal information and relationships

No Comments

No Known Activations