INDEX

Explanations

words related to various locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

rite

-0.17

è¨

-0.17

steen

-0.16

ebe

-0.16

heel

-0.16

inish

-0.15

iki

-0.15

POCH

-0.15

atcher

-0.15

edom

-0.15

POSITIVE LOGITS

emble

0.19

rex

0.16

igram

0.16

çĶ²

0.16

hta

0.16

ycl

0.15

ffen

0.15

igan

0.15

Wig

0.15

htt

0.15

Activations Density 0.025%

words related to various locations

No Comments

No Known Activations