INDEX

Explanations

names and affiliations of authors in academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

usz

-0.15

mlin

-0.15

lland

-0.15

oston

-0.15

erek

-0.14

ukes

-0.14

ajs

-0.14

loom

-0.14

é»ĺ

-0.14

POSITIVE LOGITS

irl

0.17

ibold

0.16

lesson

0.14

-shared

0.14

æł¸

0.14

arf

0.14

igned

0.13

 Dort

0.13

Bon

0.13

Activations Density 0.097%

names and affiliations of authors in academic contexts

No Comments

No Known Activations