INDEX

Explanations

words associated with legal terminology and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

aln

-0.15

umba

-0.15

undle

-0.15

Byl

-0.14

aniem

-0.14

CHAN

-0.14

uby

-0.14

le

-0.14

-0.13

agoon

-0.13

POSITIVE LOGITS

Ì£

0.16

.bc

0.15

ICODE

0.15

abelle

0.15

idis

0.14

 Ð·Ð°Ð³

0.14

oad

0.14

 inde

0.14

presso

0.14

Activations Density 0.007%

words associated with legal terminology and concepts

No Comments

No Known Activations