INDEX

Explanations

references to specific objects or entities, particularly in technical or analytical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 organ

-0.17

be

-0.16

po

-0.15

ys

-0.15

anding

-0.14

 realism

-0.14

è°·

-0.14

acing

-0.14

Nam

-0.14

ace

-0.14

POSITIVE LOGITS

ureau

0.18

aru

0.17

otts

0.16

ancers

0.15

 Ø¯ÙģØªØ±

0.15

antics

0.14

dek

0.14

YO

0.14

defines

0.14

XMLLoader

0.14

Activations Density 0.002%

references to specific objects or entities, particularly in technical or analytical contexts

No Comments

No Known Activations