INDEX

Explanations

connections and relationships expressed through conjunctions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

BOVE

-0.17

lut

-0.16

rcode

-0.14

ÏĦÎ¹ÎºÎ±

-0.14

 Sexe

-0.14

gia

-0.14

dorf

-0.14

plode

-0.14

lrt

-0.14

lom

-0.14

POSITIVE LOGITS

aul

0.18

erson

0.16

 transparent

0.14

fx

0.14

FX

0.14

ought

0.14

oust

0.14

aine

0.14

ough

0.14

iles

0.14

Activations Density 0.115%

connections and relationships expressed through conjunctions

No Comments

No Known Activations