INDEX

Explanations

keywords related to specific medical, technical, or procedural terms

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

inate

-0.16

Fab

-0.16

.RunWith

-0.15

rink

-0.14

 Harden

-0.14

.ErrorCode

-0.14

amation

-0.14

vet

-0.14

ADM

-0.14

kol

-0.13

POSITIVE LOGITS

aki

0.16

 Brandon

0.15

Hol

0.15

uar

0.15

aku

0.15

itia

0.15

spr

0.14

hit

0.14

 Holy

0.14

uard

0.14

Activations Density 0.019%

keywords related to specific medical, technical, or procedural terms

No Comments

No Known Activations