INDEX

Explanations

structural elements and formatting features commonly found in academic or formal writing, such as titles, citations, and references

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

ardless

-0.16

ctp

-0.15

reibung

-0.15

dra

-0.15

joy

-0.14

ãĥģãĥ¥

-0.14

ickey

-0.14

oot

-0.14

oker

-0.14

Ì

-0.13

POSITIVE LOGITS

olog

0.15

acher

0.14

ÑĢÑĥ

0.14

.jupiter

0.14

Rut

0.14

inen

0.14

hani

0.13

ä¸¸

0.13

Activations Density 0.007%

structural elements and formatting features commonly found in academic or formal writing, such as titles, citations, and references

No Comments

No Known Activations