INDEX

Explanations

names of locations and geographic references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

uvre

-0.18

uess

-0.16

opping

-0.16

PELL

-0.16

antan

-0.16

tap

-0.16

phan

-0.15

tap

-0.15

rowsing

-0.15

erah

-0.14

POSITIVE LOGITS

.getPort

0.18

ENTRY

0.17

mouth

0.17

intree

0.16

imli

0.15

onal

0.15

rique

0.15

åı£

0.14

RIX

0.14

avs

0.14

Activations Density 0.019%

names of locations and geographic references

No Comments

No Known Activations