INDEX

Explanations

names of prominent figures and their associated attributes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Ashe

-0.17

ADATA

-0.17

bedo

-0.16

jab

-0.16

rete

-0.15

ATYPE

-0.15

bum

-0.15

antro

-0.15

umar

-0.15

izio

-0.15

POSITIVE LOGITS

(Int

0.21

(IM

0.17

ibly

0.16

(IP

0.16

PB

0.14

CVS

0.14

 outr

0.14

(IT

0.14

/I

0.14

Tod

0.14

Activations Density 0.221%

names of prominent figures and their associated attributes in various contexts

No Comments

No Known Activations