INDEX

Explanations

the use of prepositions 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 @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Ìĥ

-0.16

áº¡t

-0.15

><![

-0.15

ayout

-0.15

_EFFECT

-0.15

ech

-0.14

amp

-0.14

 viá»ĩn

-0.14

 å¹

-0.13

cip

-0.13

POSITIVE LOGITS

pij

0.19

Browsable

0.17

oodles

0.17

 Rural

0.16

ĳľ

0.15

sit

0.14

illin

0.14

IDER

0.14

Activations Density 0.000%

the use of prepositions in context

No Comments

No Known Activations