INDEX

Explanations

specific terms or phrases associated with a certain cultural or symbolic context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ymes

-0.15

ep

-0.15

 view

-0.14

ãĤº

-0.14

 blind

-0.14

ymous

-0.14

ph

-0.14

ins

-0.13

èº

-0.13

POSITIVE LOGITS

abcdefgh

0.16

abcdefghijkl

0.16

umlu

0.15

departure

0.15

ABCDEFGHI

0.14

ech

0.14

opia

0.14

ootball

0.14

ABCDEFGHIJKLMNOP

0.14

_perms

0.14

Activations Density 0.008%

specific terms or phrases associated with a certain cultural or symbolic context

No Comments

No Known Activations