INDEX

Explanations

references to navigating or moving through physical or abstract spaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

aida

-0.16

upert

-0.15

utr

-0.15

ÙĨØ¨

-0.14

 curb

-0.14

udur

-0.14

ãĥ«ãĥĪ

-0.14

reds

-0.14

-roll

-0.13

ÑĤÐµÑĢÐ¸

-0.13

POSITIVE LOGITS

Å¼e

0.15

-lnd

0.15

otten

0.15

isman

0.14

_cmos

0.14

offsetof

0.14

 Prosper

0.14

zee

0.13

/Peak

0.13

pag

0.13

Activations Density 0.243%

references to navigating or moving through physical or abstract spaces

No Comments

No Known Activations