INDEX

Explanations

references to legal courts and appellate processes

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

agli

-0.17

itele

-0.15

oppel

-0.15

 Harden

-0.15

 Hlav

-0.15

oken

-0.14

elman

-0.14

iegel

-0.14

licas

-0.14

ikan

-0.14

POSITIVE LOGITS

.dex

0.16

ServiceProvider

0.16

ãİ

0.15

piar

0.14

ToLeft

0.14

 Garn

0.14

mediate

0.14

_asc

0.14

emb

0.14

-keys

0.14

Activations Density 0.026%

references to legal courts and appellate processes

No Comments

No Known Activations