INDEX

Explanations

phrases indicating limitations or constraints

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

cheon

-0.17

agner

-0.15

htag

-0.14

_Integer

-0.14

ipa

-0.14

 Wass

-0.14

iris

-0.14

cab

-0.13

eza

-0.13

ertext

-0.13

POSITIVE LOGITS

0.16

imes

0.15

 Farrell

0.14

0.13

SizeMode

0.13

 stal

0.13

 Cons

0.13

riel

0.13

 attempt

0.13

utherland

0.13

Activations Density 0.030%

phrases indicating limitations or constraints

No Comments

No Known Activations