INDEX

Explanations

names or terms related to specific subjects or items

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

affer

-0.16

 Admir

-0.15

pcl

-0.15

ville

-0.15

orus

-0.15

fo

-0.15

ynes

-0.15

 Villa

-0.14

yna

-0.14

tb

-0.14

POSITIVE LOGITS

/GPL

0.16

endi

0.15

 often

0.15

ektor

0.14

_Lean

0.14

 usually

0.14

 rarely

0.14

 demanding

0.14

 Ð²ÑģÑĤ

0.14

oder

0.14

Activations Density 0.079%

names or terms related to specific subjects or items

No Comments

No Known Activations