INDEX

Explanations

legal terminology and references to laws and agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

issen

-0.16

unkt

-0.15

ãģĵãĤĵãģ«ãģ¡ãģ¯

-0.15

 Tactical

-0.14

pit

-0.14

icker

-0.13

 Colomb

-0.13

urse

-0.13

forgettable

-0.13

POSITIVE LOGITS

.onView

0.16

orda

0.15

aid

0.15

ettle

0.14

BufferSize

0.14

inst

0.14

isman

0.14

stan

0.14

(Method

0.13

Activations Density 0.010%

legal terminology and references to laws and agreements

No Comments

No Known Activations