INDEX

Explanations

proper nouns and identifiers relevant to location and context

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

Ã©o

-0.16

ourg

-0.16

 Opposition

-0.16

_:*

-0.15

Millis

-0.15

Ð¾Ð½Ð¾Ð²

-0.15

_vect

-0.15

 oppos

-0.15

ëĦ

-0.14

ë¡¤

-0.14

POSITIVE LOGITS

etri

0.16

run

0.15

 quote

0.15

ivity

0.15

 Poster

0.14

SetActive

0.14

quets

0.14

 sort

0.14

hol

0.14

 lands

0.14

Activations Density 0.005%

proper nouns and identifiers relevant to location and context

No Comments

No Known Activations