INDEX

Explanations

symbols and special characters in 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 @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

lah

-0.16

arin

-0.16

alian

-0.15

eland

-0.14

RH

-0.14

oren

-0.14

iba

-0.14

aceae

-0.13

 Verd

-0.13

ivor

-0.13

POSITIVE LOGITS

PIO

0.17

ideon

0.15

hap

0.14

.annotation

0.14

 synthetic

0.14

BuilderInterface

0.14

.nlm

0.14

ektiv

0.14

subcategory

0.14

 Shelf

0.14

Activations Density 0.000%

symbols and special characters in the text

No Comments

No Known Activations