INDEX

Explanations

references to specific locations and directions within a geographic context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

illow

-0.16

mpar

-0.16

anford

-0.15

mdl

-0.15

mdir

-0.15

ingen

-0.14

.PropTypes

-0.14

assin

-0.14

rane

-0.14

Ð²Ð°Ð½Ð¸Ðµ

-0.14

POSITIVE LOGITS

uing

0.15

empl

0.15

 Feld

0.14

Å¡k

0.14

Dat

0.14

osa

0.14

 Flush

0.14

Bu

0.14

Ã³ln

0.14

 Burl

0.13

Activations Density 0.083%

references to specific locations and directions within a geographic context

No Comments

No Known Activations