INDEX

Explanations

terms related to legal proceedings and trials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

osu

-0.16

unday

-0.15

agrid

-0.15

åĩĿ

-0.15

ãĤħ

-0.15

smith

-0.15

inae

-0.14

ummy

-0.14

.ali

-0.14

_PRIV

-0.14

POSITIVE LOGITS

 Gall

0.16

niÄį

0.15

ses

0.15

morgan

0.15

hta

0.14

illum

0.14

arness

0.13

quake

0.13

ota

0.13

Activations Density 0.198%

terms related to legal proceedings and trials

No Comments

No Known Activations