INDEX

Explanations

references to geographical locations or landmarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Fell

-0.16

 Ð·Ð°Ð»

-0.15

-Core

-0.15

rawn

-0.14

orum

-0.14

dni

-0.14

Tw

-0.13

branch

-0.13

hei

-0.13

ystal

-0.13

POSITIVE LOGITS

eken

0.21

ubat

0.19

ophil

0.17

ÐĲÑĢÑħÑĸÐ²

0.16

 Roch

0.16

 Rape

0.16

LIK

0.15

aupt

0.15

 Provid

0.15

 Hague

0.15

Activations Density 0.023%

references to geographical locations or landmarks

No Comments

No Known Activations