INDEX

Explanations

names and credentials of individuals, particularly in professional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ollah

-0.15

rone

-0.14

rapped

-0.14

uran

-0.14

avis

-0.14

blick

-0.14

ouz

-0.13

liÅ¾

-0.13

omb

-0.13

POSITIVE LOGITS

 graduate

0.40

 gradu

0.40

 grad

0.39

 graduated

0.39

grad

0.39

 earned

0.37

 Grad

0.37

earned

0.35

 obtained

0.35

 earning

0.35

Activations Density 0.262%

names and credentials of individuals, particularly in professional contexts

No Comments

No Known Activations