INDEX

Explanations

references to props, particularly in a technical or production context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

iac

-0.20

ered

-0.17

erd

-0.17

erk

-0.16

icast

-0.15

istics

-0.15

 comb

-0.14

VENTORY

-0.14

liness

-0.14

ematic

-0.14

POSITIVE LOGITS

daily

0.16

hecy

0.15

 Prop

0.14

 daily

0.14

hec

0.14

seudo

0.14

enheim

0.14

[prop

0.13

razier

0.13

 prop

0.13

Activations Density 0.036%

references to props, particularly in a technical or production context

No Comments

No Known Activations