INDEX

Explanations

occurrences of the word "Nach" indicating a focus on sequential events or narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

arium

-0.16

 Appalachian

-0.15

ebek

-0.15

bis

-0.15

ROUT

-0.14

anford

-0.14

stakes

-0.14

ENSOR

-0.14

ationale

-0.14

umble

-0.14

POSITIVE LOGITS

è¯Ŀ

0.17

igli

0.16

fol

0.16

ts

0.16

ward

0.15

illy

0.15

 mÄĽ

0.15

olen

0.15

ives

0.14

oice

0.14

Activations Density 0.010%

occurrences of the word "Nach" indicating a focus on sequential events or narratives

No Comments

No Known Activations