INDEX

Explanations

instances of discovery or findings in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ialog

-0.18

ospace

-0.15

ereotype

-0.15

ilyn

-0.15

 stan

-0.15

adic

-0.15

IEL

-0.15

amp

-0.14

.lv

-0.14

setError

-0.14

POSITIVE LOGITS

Dow

0.16

 tapped

0.15

uber

0.15

down

0.14

ident

0.14

 Ident

0.14

lands

0.14

 Mahm

0.14

dma

0.14

tr

0.14

Activations Density 0.207%

instances of discovery or findings in a narrative context

No Comments

No Known Activations