INDEX

Explanations

specific phrases and words indicating associations or connections

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

illion

-0.16

ilha

-0.16

yal

-0.15

enia

-0.15

-slot

-0.15

Alv

-0.15

 istih

-0.14

orama

-0.14

ierz

-0.14

POSITIVE LOGITS

 åº¦

0.16

 Vince

0.14

Taj

0.14

Hun

0.14

lt

0.14

kate

0.13

ars

0.13

iT

0.13

Activations Density 0.001%

specific phrases and words indicating associations or connections

No Comments

No Known Activations