INDEX

Explanations

specific product features or specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

unge

-0.16

eron

-0.14

ong

-0.14

ary

-0.14

rock

-0.14

iny

-0.14

este

-0.14

ener

-0.13

tex

-0.13

Äįka

-0.13

POSITIVE LOGITS

-fontawesome

0.16

¯u

0.15

_exempt

0.14

usercontent

0.14

Ð±Ñĥ

0.14

æ¯Ľ

0.14

 UIStoryboard

0.14

wdx

0.14

ìļĶ

0.13

Activations Density 0.006%

specific product features or specifications

No Comments

No Known Activations