INDEX

Explanations

references to previous events or occurrences

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

edm

-0.18

uml

-0.15

okit

-0.15

kt

-0.14

shell

-0.14

app

-0.14

iens

-0.14

eg

-0.14

udge

-0.14

POSITIVE LOGITS

/current

0.21

mente

0.17

-generation

0.17

carousel

0.17

Ħìŀ¬

0.17

zeitig

0.16

CLUDING

0.16

lava

0.15

ainen

0.15

.fp

0.15

Activations Density 0.026%

references to previous events or occurrences

No Comments

No Known Activations