INDEX

Explanations

references to figures, tables, and awards in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

urse

-0.16

 virgin

-0.16

_decision

-0.15

ÑĪÐ¸Ð²

-0.15

.scalablytyped

-0.15

uzzy

-0.15

ÑĩÐ°

-0.15

 flatt

-0.15

 Nurse

-0.14

.gdx

-0.14

POSITIVE LOGITS

 object

0.18

 pose

0.17

object

0.17

_visibility

0.16

/object

0.16

 proposals

0.16

-object

0.16

 grounding

0.16

/Object

0.16

ego

0.15

Activations Density 0.005%

references to figures, tables, and awards in scientific contexts

No Comments

No Known Activations