INDEX

Explanations

patterns indicating agreements and interactions in legal or formal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

_mD

-0.16

Ð°ÑĢÐ¾Ð´

-0.16

["$

-0.15

sein

-0.15

roje

-0.15

ROTO

-0.14

Castle

-0.14

_tD

-0.14

à¸·à¸Ļ

-0.14

jal

-0.14

POSITIVE LOGITS

0.18

 absolute

0.15

 Reason

0.15

bob

0.15

 epic

0.14

bond

0.14

Activations Density 0.002%

patterns indicating agreements and interactions in legal or formal contexts

No Comments

No Known Activations