INDEX

Explanations

mentions of specific locations, particularly Oakland, and relevant words associated with them

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

+offset

-0.18

 orgÃ¡n

-0.17

ANTLR

-0.17

_oauth

-0.17

/object

-0.17

imizer

-0.16

nez

-0.16

opers

-0.15

orted

-0.15

 á»ĳng

-0.15

POSITIVE LOGITS

entimes

0.19

Ø§Ø®Ø±

0.19

ahoma

0.18

verture

0.18

.uk

0.18

awa

0.17

yssey

0.17

 fashioned

0.17

anagan

0.17

Activations Density 1.124%

mentions of specific locations, particularly Oakland, and relevant words associated with them

No Comments

No Known Activations