INDEX

Explanations

the use of spatial and directional terms in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÏĢÎ¬

-0.14

çĽ¤

-0.14

istros

-0.14

æķ·

-0.14

 longitud

-0.13

yster

-0.13

isma

-0.13

Å¼

-0.13

 plains

-0.13

iser

-0.13

POSITIVE LOGITS

 corner

1.27

 corners

1.11

 Corner

1.05

corner

1.04

Corner

0.99

-corner

0.96

_corner

0.79

è§Ĵ

0.63

_corners

0.61

 Corn

0.58

Activations Density 0.159%

the use of spatial and directional terms in context

No Comments

No Known Activations

the use of spatial and directional terms in context

No Comments

No Known Activations