INDEX

Explanations

mentions of specific names or terms related to various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

etrain

-0.16

uous

-0.14

ulus

-0.14

OO

-0.14

ussed

-0.14

 verte

-0.14

ough

-0.13

orb

-0.13

ÑĥÑĩ

-0.13

osaic

-0.13

POSITIVE LOGITS

ughters

0.18

quan

0.17

YLON

0.17

oxetine

0.16

èĮ

0.15

vid

0.15

 indef

0.15

hood

0.15

kÅ¯

0.15

segue

0.14

Activations Density 0.042%

mentions of specific names or terms related to various contexts

No Comments

No Known Activations