INDEX

Explanations

terms related to libel and defamation in the context of legal discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

lobs

-0.16

elsen

-0.16

 å¼

-0.15

gaard

-0.15

 Neutral

-0.14

adio

-0.14

 neutral

-0.14

esign

-0.14

ropa

-0.14

Neutral

-0.14

POSITIVE LOGITS

 Aspen

0.15

Occurs

0.15

Ort

0.14

Mez

0.14

 slur

0.14

unken

0.14

 Prel

0.14

 omap

0.13

Insets

0.13

 preliminary

0.13

Activations Density 0.007%

terms related to libel and defamation in the context of legal discussions

No Comments

No Known Activations