INDEX

Explanations

geographical locations or references in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 base

-0.16

 Base

-0.16

uhl

-0.14

/tab

-0.13

 bases

-0.13

 posted

-0.13

/base

-0.13

ume

-0.13

 centroid

-0.13

POSITIVE LOGITS

/bower

0.17

ancia

0.16

fov

0.15

venida

0.15

ainen

0.15

 ########.

0.14

quina

0.14

odia

0.14

ARDS

0.14

ensis

0.14

Activations Density 0.092%

geographical locations or references in text

No Comments

No Known Activations