INDEX

Explanations

references to specific labels or categories within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ald

-0.16

 è¶

-0.15

Ash

-0.15

och

-0.14

atten

-0.14

Ð°ÑĢÐ°ÑĤ

-0.14

ash

-0.14

Ash

-0.14

uc

-0.13

(of

-0.13

POSITIVE LOGITS

nonnull

0.15

aeda

0.15

iform

0.15

olith

0.15

idel

0.15

ewise

0.15

losion

0.14

ledi

0.14

led

0.14

oku

0.14

Activations Density 0.002%

references to specific labels or categories within the text

No Comments

No Known Activations